Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Knowledge Evaluation on Cmmlu_c

36.88Accuracy

ML (Q3)

31.867233.168634.4735.7714Apr 22, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.04
36.88
2026.04
36.08
2026.04
35.81
2026.04
34.71
2026.04
34.66
2026.04
34.45
2026.04
32.06